I have successfully defend my Ph.D. dissertation “Adversarial Transferability and Generalization in Robust Deep Learning”. I will join Dr. Seung-Jong Park group as a postdoc working on LLM research.
Our two papers LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogate and CR-SAM: Curvature Regularized Sharpness-Aware Minimization are accepted by AAAI Conference on Artificial Intelligence (AAAI) 2024! Acceptance rate: 19% (2342/12100)
Our paper GNP Attack: Transferable Adversarial Examples via Gradient Norm Penalty has been accepted by International Conference of Image Processing 2023!